Vision

Nested swiss-knife reference for image understanding — a decision tree that routes between three paths depending on what the agent has access to: (1) the built-in `vision` tool if the LLM provider supports image input, (2) the sibling `minimax-cli` reference if a usable MiniMax preset/key slot is available, or (3) a local Hugging Face VLM via the bundled `scripts/describe.py` if neither — offline, free, slow. Read this when you need to describe, OCR, or critique an image and you're not sure which path applies.

lingtai-ai Updated 509 repo stars
LingTai portal showing a live local network of long-lived project agents

File contents

lingtai-ai/lingtai commit 6a2f7db4ac Runs: lingtai-ai/lingtai-issue-report

Frequently asked questions

npx get-skill add lingtai-ai/vision